Skip to main content
Glama

historique

Read-onlyIdempotent

Retrieve a readable summary of a PLC variable's history over a time window: min, max, mean and peak-preserving curves for numeric values, or state-change lists for booleans and codes.

Instructions

Historique d'une variable sur une période, résumé pour rester lisible.

    Variables numériques : min, max (avec horodatage), moyenne et une courbe sous-échantillonnée qui
    conserve les pics. Booléens et codes : liste des changements d'état.

    Args:
        chemin: variable, ex. « Four2.Temperature ».
        periode: durée glissante jusqu'à maintenant (« 30min », « 8h », « 2j ») ou « nuit » (22 h → 6 h).
        debut: date ISO 8601 de début (heure locale), prioritaire sur periode. Ex. « 2026-11-19T02:30 ».
        fin: date ISO 8601 de fin (défaut : maintenant).
    

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "chemin": "<chemin>"
    },
    "name": "historique"
  }
}

Input Schema

NameRequiredDescriptionDefault
finNo
debutNo
cheminYes
periodeNo24h

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, so the safety profile is covered. Beyond that, the description discloses the actual response shape: min/max with timestamps plus a peak-preserving downsampled curve for numeric variables, and a state-change list for booleans/codes. It says nothing about data volume limits, unavailable variables, or error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The summary of what the tool does and what it returns is front-loaded and the per-parameter notes follow in a predictable docstring layout, with no filler sentences. The structure is slightly conventional (Args block) rather than maximally agent-oriented, but every line carries information absent from the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only query tool with an output schema, the description covers intent, input formats, precedence rules and the two output shapes; return-value detail can be delegated to the output schema. Minor gaps remain around units, timezone handling beyond 'heure locale', and behaviour when the path is unknown.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the full burden and it does: all four parameters are documented with a concrete example path, accepted duration formats ('30min', '8h', '2j'), the special 'nuit' value with its 22h→6h meaning, ISO 8601 local-time examples, the default of 'fin' to now, and the explicit precedence of 'debut' over 'periode'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb and resource: retrieve the history of a named variable over a period, returned in summarized form. It does not explicitly contrast itself with neighbours like lire_variable or journal_evenements, so an agent must infer that this is the time-series tool rather than the current-value or event-log tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied by the parameter documentation (sliding period vs. explicit start date, with 'debut' taking precedence over 'periode'), which tells the agent how to call it but not when to prefer it over a sibling. There are no exclusions or named alternatives, so the when-to-use decision is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.